Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    pronouns related to groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    біль
    -0.54
    tand
    -0.49
    urs
    -0.48
    andaan
    -0.47
     Bue
    -0.47
    関連記事
    -0.47
     Chas
    -0.46
    铭
    -0.46
    URLException
    -0.46
     fencing
    -0.46
    POSITIVE LOGITS
     themselves
    1.48
    THEY
    1.43
    themselves
    1.39
     THEY
    1.36
     they
    1.33
    Their
    1.27
    They
    1.24
     They
    1.20
     Their
    1.12
    their
    1.12
    Act Density 0.227%

    No Known Activations